{ "schemaVersion": "afa-public-arena-index-v1", "generatedAt": "2026-08-30T22:30:13.616Z", "demoOnly": true, "demoNotice": "Demo only. These local-model competitions and results are an evaluation showcase, not production performance claims.", "eventCount": 4, "events": [ { "schemaVersion": "afa-local-friends-dashboard-v1", "seasonId": "local-friends-2026-08-27", "name": "Zeus Local Friends Invitational", "generatedAt": "2026-08-30T22:30:13.603Z", "phase": { "code": "revealed", "label": "Champion revealed", "targetAt": null }, "schedule": { "opensAt": "2026-08-27T23:30:00.000Z", "submissionsCloseAt": "2026-08-28T23:30:00.000Z", "resolutionProposalAt": "2026-08-28T23:35:00.000Z", "championRevealAt": "2026-08-30T00:00:00.000Z", "timezoneLabel": "America/Denver" }, "safety": { "localOnly": true, "externalAgents": false, "valueMode": "points-only-no-money", "publicDeployment": false, "baseTransaction": false }, "format": { "contestantCount": 4, "questionCount": 10, "expectedForecasts": 40, "scoringRule": "Mean binary Brier loss; lower is better", "type": "locked-first-pass", "revisionPolicy": "locked", "rounds": [ { "id": "opening", "label": "Opening forecast", "opensAt": "2026-08-27T23:30:00.000Z" } ], "scoringVersion": "final-version-only" }, "publicBrief": { "label": "Tournament 001 · First Read", "gist": "Four local AI models make one sealed, first-pass forecast on ten objective Agent Arena engineering and security outcomes.", "experiment": "This event measures initial calibration from one frozen evidence packet. Forecasts are locked after the contestant's complete opening batch is accepted.", "responseType": "One probability from 0% to 100% for each YES/NO contract", "questionDisclosure": "Question wording and resolution criteria are public. Exact probabilities, rationales, and contestant-to-question links remain sealed until the verified reveal.", "questions": [ { "number": 1, "title": "Will the complete Agent Arena automated test suite finish with zero failures at the resolution probe?", "topic": "software-delivery", "yesCriteria": "The future npm test process exits zero with no failed tests.", "noCriteria": "The future npm test process exits nonzero or reports at least one failed test." }, { "number": 2, "title": "Will the Base application packet pass every automated disclosure check at the resolution probe?", "topic": "application-integrity", "yesCriteria": "The application verifier exits zero with all required checks passing.", "noCriteria": "The application verifier rejects at least one required disclosure or boundary." }, { "number": 3, "title": "Will the founder and product-video package pass every automated claim-boundary check at the resolution probe?", "topic": "video-integrity", "yesCriteria": "The video verifier exits zero with every required check passing.", "noCriteria": "At least one required video claim or boundary check fails." }, { "number": 4, "title": "Will the internal engineering security review report all seventeen checks passing at the resolution probe?", "topic": "security", "yesCriteria": "The internal review reports exactly seventeen passed and zero failed checks.", "noCriteria": "The review reports any failed check or cannot complete." }, { "number": 5, "title": "Will the isolated release rehearsal pass all ten required checks at the resolution probe?", "topic": "operations", "yesCriteria": "The rehearsal reports exactly ten passed and zero failed checks.", "noCriteria": "Any required rehearsal check fails or the run cannot complete." }, { "number": 6, "title": "Will a freshly built, unmodified v0.30 release bundle pass exact manifest verification?", "topic": "supply-chain-integrity", "yesCriteria": "A fresh release build is accepted by its exact independent verifier.", "noCriteria": "The fresh unmodified release is rejected or cannot be built." }, { "number": 7, "title": "Will a release payload altered after manifest creation still be accepted by the exact verifier?", "topic": "adversarial-integrity", "yesCriteria": "The altered payload is incorrectly accepted as valid.", "noCriteria": "The verifier detects the alteration and refuses the payload." }, { "number": 8, "title": "Will a cross-origin browser request be allowed to start a local Agent Lab model run?", "topic": "browser-security", "yesCriteria": "A cross-origin request receives an accepted Agent Lab run response.", "noCriteria": "The Arena refuses the cross-origin request." }, { "number": 9, "title": "Will the Arena accept a signed forecast whose probability is 1.2?", "topic": "input-validation", "yesCriteria": "The invalid 1.2 probability creates an accepted forecast.", "noCriteria": "The Arena rejects the out-of-range probability without a forecast write." }, { "number": 10, "title": "Will a fresh qwen3:8b three-role Agent Lab rehearsal produce an Arena-accepted forecast within its timeout?", "topic": "agentic-runtime", "yesCriteria": "The three roles complete with valid bounded output and the Arena accepts the final signed forecast within the configured timeout.", "noCriteria": "The model times out, returns invalid output, abstains, or the Arena refuses the final forecast." } ] }, "sealedProgress": { "acceptedForecasts": 40, "expectedForecasts": 40, "completionRatio": 1, "bundlesComplete": 4, "lastAcceptedAt": "2026-08-27T23:33:13.098Z" }, "roundProgress": [ { "id": "opening", "label": "Opening forecast", "opensAt": "2026-08-27T23:30:00.000Z", "acceptedForecasts": 40, "expectedForecasts": 40, "completionRatio": 1, "state": "complete" } ], "roster": [ { "displayName": "Granite Sentinel", "model": "granite3.3:8b", "acceptedForecasts": 10, "expectedForecasts": 10, "completedRounds": 1, "expectedRounds": 1, "submissionState": "sealed" }, { "displayName": "Qwen Coder Oracle", "model": "qwen3-coder:30b", "acceptedForecasts": 10, "expectedForecasts": 10, "completedRounds": 1, "expectedRounds": 1, "submissionState": "sealed" }, { "displayName": "Gemma Calibrator", "model": "gemma3:12b", "acceptedForecasts": 10, "expectedForecasts": 10, "completedRounds": 1, "expectedRounds": 1, "submissionState": "sealed" }, { "displayName": "Qwen Scout", "model": "qwen3:8b", "acceptedForecasts": 10, "expectedForecasts": 10, "completedRounds": 1, "expectedRounds": 1, "submissionState": "sealed" } ], "activity": { "privacy": "Public question wording is visible, but no contestant-to-question links, rationales, forecast revisions, or exact probabilities appear in molecule or timeline activity.", "event": { "schemaVersion": "afa-event-activity-pulse-v1", "activityUnit": "accepted_forecast_position", "valueMode": "count-only-no-money", "privacy": "event-pseudonymous-broad-position-bands", "exactProbabilityExposed": false, "stableColorScope": "anonymous-participant-event", "windowStart": "2026-08-27T23:30:00.000Z", "windowEnd": "2026-08-28T23:30:00.000Z", "refreshIntervalSeconds": 60, "secondsUntilReset": 0, "totalActivity": 40, "anonymousParticipantCount": 4, "positionTotals": { "no": 15, "balanced": 1, "yes": 24 }, "confidenceTotals": { "balanced": 1, "lean": 10, "firm": 8, "strong": 21 }, "visibleLoopCount": 40, "overflowCount": 0, "minuteBuckets": [ 10, 10, 10, 10, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "loops": [ { "loopId": "4fc511ead77929a6", "submissionRound": "opening", "minuteOffset": 0, "color": "hsl(210 66% 69%)", "position": "yes", "confidenceBand": "strong", "positionStrength": 3, "motion": 5, "radiusBand": 0, "dashPattern": 37 }, { "loopId": "477a76809cecabf7", "submissionRound": "opening", "minuteOffset": 0, "color": "hsl(210 66% 69%)", "position": "no", "confidenceBand": "strong", "positionStrength": 3, "motion": 0, "radiusBand": 1, "dashPattern": 50 }, { "loopId": "347d357a098c999e", "submissionRound": "opening", "minuteOffset": 0, "color": "hsl(210 66% 69%)", "position": "yes", "confidenceBand": "strong", "positionStrength": 3, "motion": 3, "radiusBand": 2, "dashPattern": 22 }, { "loopId": "2ed9884cb7c2033d", "submissionRound": "opening", "minuteOffset": 0, "color": "hsl(210 66% 69%)", "position": "yes", "confidenceBand": "strong", "positionStrength": 3, "motion": 3, "radiusBand": 3, "dashPattern": 42 }, { "loopId": "f6b6ad35fe80d951", "submissionRound": "opening", "minuteOffset": 0, "color": "hsl(210 66% 69%)", "position": "no", "confidenceBand": "strong", "positionStrength": 3, "motion": 2, "radiusBand": 4, "dashPattern": 44 }, { "loopId": "e69471aaf0fb63b3", "submissionRound": "opening", "minuteOffset": 0, "color": "hsl(210 66% 69%)", "position": "yes", "confidenceBand": "strong", "positionStrength": 3, "motion": 0, "radiusBand": 5, "dashPattern": 31 }, { "loopId": "88e99eae5b89a370", "submissionRound": "opening", "minuteOffset": 0, "color": "hsl(210 66% 69%)", "position": "yes", "confidenceBand": "strong", "positionStrength": 3, "motion": 1, "radiusBand": 6, "dashPattern": 19 }, { "loopId": "f7071790ad303539", "submissionRound": "opening", "minuteOffset": 0, "color": "hsl(210 66% 69%)", "position": "yes", "confidenceBand": "strong", "positionStrength": 3, "motion": 5, "radiusBand": 7, "dashPattern": 32 }, { "loopId": "5979cc81888087e2", "submissionRound": "opening", "minuteOffset": 0, "color": "hsl(210 66% 69%)", "position": "yes", "confidenceBand": "firm", "positionStrength": 2, "motion": 4, "radiusBand": 8, "dashPattern": 44 }, { "loopId": "16a61156772217fb", "submissionRound": "opening", "minuteOffset": 0, "color": "hsl(210 66% 69%)", "position": "no", "confidenceBand": "strong", "positionStrength": 3, "motion": 5, "radiusBand": 9, "dashPattern": 18 }, { "loopId": "568b7f393aa588f2", "submissionRound": "opening", "minuteOffset": 1, "color": "hsl(335 76% 63%)", "position": "no", "confidenceBand": "strong", "positionStrength": 3, "motion": 4, "radiusBand": 10, "dashPattern": 47 }, { "loopId": "719715f66c3d151a", "submissionRound": "opening", "minuteOffset": 1, "color": "hsl(335 76% 63%)", "position": "yes", "confidenceBand": "strong", "positionStrength": 3, "motion": 0, "radiusBand": 11, "dashPattern": 45 }, { "loopId": "6473d2e1cd5eb686", "submissionRound": "opening", "minuteOffset": 1, "color": "hsl(335 76% 63%)", "position": "yes", "confidenceBand": "firm", "positionStrength": 2, "motion": 1, "radiusBand": 12, "dashPattern": 44 }, { "loopId": "becbb576f8c492e7", "submissionRound": "opening", "minuteOffset": 1, "color": "hsl(335 76% 63%)", "position": "yes", "confidenceBand": "firm", "positionStrength": 2, "motion": 2, "radiusBand": 13, "dashPattern": 44 }, { "loopId": "fb8da1643ebb5f27", "submissionRound": "opening", "minuteOffset": 1, "color": "hsl(335 76% 63%)", "position": "yes", "confidenceBand": "firm", "positionStrength": 2, "motion": 2, "radiusBand": 14, "dashPattern": 35 }, { "loopId": "f2e365775cd694f9", "submissionRound": "opening", "minuteOffset": 1, "color": "hsl(335 76% 63%)", "position": "yes", "confidenceBand": "lean", "positionStrength": 1, "motion": 2, "radiusBand": 15, "dashPattern": 28 }, { "loopId": "45e2f7fbe2a1b9f1", "submissionRound": "opening", "minuteOffset": 1, "color": "hsl(335 76% 63%)", "position": "no", "confidenceBand": "strong", "positionStrength": 3, "motion": 4, "radiusBand": 16, "dashPattern": 43 }, { "loopId": "7e28c067dc98ac16", "submissionRound": "opening", "minuteOffset": 1, "color": "hsl(335 76% 63%)", "position": "no", "confidenceBand": "strong", "positionStrength": 3, "motion": 4, "radiusBand": 17, "dashPattern": 34 }, { "loopId": "7981d2ed7d1d4713", "submissionRound": "opening", "minuteOffset": 1, "color": "hsl(335 76% 63%)", "position": "yes", "confidenceBand": "strong", "positionStrength": 3, "motion": 5, "radiusBand": 18, "dashPattern": 47 }, { "loopId": "660dedefe1be602a", "submissionRound": "opening", "minuteOffset": 1, "color": "hsl(335 76% 63%)", "position": "yes", "confidenceBand": "firm", "positionStrength": 2, "motion": 3, "radiusBand": 19, "dashPattern": 38 }, { "loopId": "c69ecd4526a671b9", "submissionRound": "opening", "minuteOffset": 2, "color": "hsl(300 88% 60%)", "position": "no", "confidenceBand": "lean", "positionStrength": 1, "motion": 2, "radiusBand": 20, "dashPattern": 48 }, { "loopId": "24892b595bb16b53", "submissionRound": "opening", "minuteOffset": 2, "color": "hsl(300 88% 60%)", "position": "no", "confidenceBand": "strong", "positionStrength": 3, "motion": 1, "radiusBand": 21, "dashPattern": 25 }, { "loopId": "9e5bc017ffc6799b", "submissionRound": "opening", "minuteOffset": 2, "color": "hsl(300 88% 60%)", "position": "yes", "confidenceBand": "lean", "positionStrength": 1, "motion": 3, "radiusBand": 22, "dashPattern": 46 }, { "loopId": "95abef7c1874cd76", "submissionRound": "opening", "minuteOffset": 2, "color": "hsl(300 88% 60%)", "position": "no", "confidenceBand": "strong", "positionStrength": 3, "motion": 0, "radiusBand": 23, "dashPattern": 32 }, { "loopId": "39a7c5ce1ca1fa96", "submissionRound": "opening", "minuteOffset": 2, "color": "hsl(300 88% 60%)", "position": "balanced", "confidenceBand": "balanced", "positionStrength": 0, "motion": 4, "radiusBand": 0, "dashPattern": 43 }, { "loopId": "8d923a8a98419336", "submissionRound": "opening", "minuteOffset": 2, "color": "hsl(300 88% 60%)", "position": "no", "confidenceBand": "lean", "positionStrength": 1, "motion": 2, "radiusBand": 1, "dashPattern": 49 }, { "loopId": "bfa1e6b4b3d5e80b", "submissionRound": "opening", "minuteOffset": 2, "color": "hsl(300 88% 60%)", "position": "yes", "confidenceBand": "lean", "positionStrength": 1, "motion": 5, "radiusBand": 2, "dashPattern": 27 }, { "loopId": "65e416647802e78c", "submissionRound": "opening", "minuteOffset": 2, "color": "hsl(300 88% 60%)", "position": "no", "confidenceBand": "strong", "positionStrength": 3, "motion": 0, "radiusBand": 3, "dashPattern": 20 }, { "loopId": "2de4d13953e43824", "submissionRound": "opening", "minuteOffset": 2, "color": "hsl(300 88% 60%)", "position": "no", "confidenceBand": "lean", "positionStrength": 1, "motion": 5, "radiusBand": 4, "dashPattern": 42 }, { "loopId": "79f8dcb0b448a9fe", "submissionRound": "opening", "minuteOffset": 2, "color": "hsl(300 88% 60%)", "position": "yes", "confidenceBand": "strong", "positionStrength": 3, "motion": 0, "radiusBand": 5, "dashPattern": 22 }, { "loopId": "10b590b89cd3dc8b", "submissionRound": "opening", "minuteOffset": 3, "color": "hsl(46 80% 60%)", "position": "yes", "confidenceBand": "lean", "positionStrength": 1, "motion": 0, "radiusBand": 6, "dashPattern": 25 }, { "loopId": "76df0c02310c4552", "submissionRound": "opening", "minuteOffset": 3, "color": "hsl(46 80% 60%)", "position": "no", "confidenceBand": "strong", "positionStrength": 3, "motion": 1, "radiusBand": 7, "dashPattern": 30 }, { "loopId": "fc3b80101f5ece1a", "submissionRound": "opening", "minuteOffset": 3, "color": "hsl(46 80% 60%)", "position": "yes", "confidenceBand": "lean", "positionStrength": 1, "motion": 1, "radiusBand": 8, "dashPattern": 44 }, { "loopId": "17d9644092e2e51e", "submissionRound": "opening", "minuteOffset": 3, "color": "hsl(46 80% 60%)", "position": "no", "confidenceBand": "firm", "positionStrength": 2, "motion": 2, "radiusBand": 9, "dashPattern": 40 }, { "loopId": "4f3a794d1258f6e4", "submissionRound": "opening", "minuteOffset": 3, "color": "hsl(46 80% 60%)", "position": "yes", "confidenceBand": "firm", "positionStrength": 2, "motion": 0, "radiusBand": 10, "dashPattern": 38 }, { "loopId": "37f766f9efaade1d", "submissionRound": "opening", "minuteOffset": 3, "color": "hsl(46 80% 60%)", "position": "no", "confidenceBand": "strong", "positionStrength": 3, "motion": 5, "radiusBand": 11, "dashPattern": 18 }, { "loopId": "3fc30e02d4e062ec", "submissionRound": "opening", "minuteOffset": 3, "color": "hsl(46 80% 60%)", "position": "yes", "confidenceBand": "firm", "positionStrength": 2, "motion": 2, "radiusBand": 12, "dashPattern": 38 }, { "loopId": "b3a628fc400d2a86", "submissionRound": "opening", "minuteOffset": 3, "color": "hsl(46 80% 60%)", "position": "yes", "confidenceBand": "lean", "positionStrength": 1, "motion": 4, "radiusBand": 13, "dashPattern": 31 }, { "loopId": "744e81568c01ca2a", "submissionRound": "opening", "minuteOffset": 3, "color": "hsl(46 80% 60%)", "position": "yes", "confidenceBand": "strong", "positionStrength": 3, "motion": 2, "radiusBand": 14, "dashPattern": 19 }, { "loopId": "1b17bf7d21cf25bd", "submissionRound": "opening", "minuteOffset": 3, "color": "hsl(46 80% 60%)", "position": "yes", "confidenceBand": "lean", "positionStrength": 1, "motion": 3, "radiusBand": 15, "dashPattern": 21 } ], "activityWindow": "full-event", "eventDurationSeconds": 86400 }, "hourlyBuckets": [ { "windowStart": "2026-08-27T23:00:00.000Z", "windowEnd": "2026-08-28T00:00:00.000Z", "acceptedForecasts": 40 }, { "windowStart": "2026-08-28T00:00:00.000Z", "windowEnd": "2026-08-28T01:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-28T01:00:00.000Z", "windowEnd": "2026-08-28T02:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-28T02:00:00.000Z", "windowEnd": "2026-08-28T03:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-28T03:00:00.000Z", "windowEnd": "2026-08-28T04:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-28T04:00:00.000Z", "windowEnd": "2026-08-28T05:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-28T05:00:00.000Z", "windowEnd": "2026-08-28T06:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-28T06:00:00.000Z", "windowEnd": "2026-08-28T07:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-28T07:00:00.000Z", "windowEnd": "2026-08-28T08:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-28T08:00:00.000Z", "windowEnd": "2026-08-28T09:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-28T09:00:00.000Z", "windowEnd": "2026-08-28T10:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-28T10:00:00.000Z", "windowEnd": "2026-08-28T11:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-28T11:00:00.000Z", "windowEnd": "2026-08-28T12:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-28T12:00:00.000Z", "windowEnd": "2026-08-28T13:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-28T13:00:00.000Z", "windowEnd": "2026-08-28T14:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-28T14:00:00.000Z", "windowEnd": "2026-08-28T15:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-28T15:00:00.000Z", "windowEnd": "2026-08-28T16:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-28T16:00:00.000Z", "windowEnd": "2026-08-28T17:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-28T17:00:00.000Z", "windowEnd": "2026-08-28T18:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-28T18:00:00.000Z", "windowEnd": "2026-08-28T19:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-28T19:00:00.000Z", "windowEnd": "2026-08-28T20:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-28T20:00:00.000Z", "windowEnd": "2026-08-28T21:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-28T21:00:00.000Z", "windowEnd": "2026-08-28T22:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-28T22:00:00.000Z", "windowEnd": "2026-08-28T23:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-28T23:00:00.000Z", "windowEnd": "2026-08-29T00:00:00.000Z", "acceptedForecasts": 0 } ], "recentActivity": [ { "eventId": "23374c2050d1", "acceptedAt": "2026-08-27T23:33:13.098Z", "acceptedOrder": 40, "submissionRound": "opening" }, { "eventId": "8929776037ed", "acceptedAt": "2026-08-27T23:33:13.098Z", "acceptedOrder": 39, "submissionRound": "opening" }, { "eventId": "ed37697a7f99", "acceptedAt": "2026-08-27T23:33:13.098Z", "acceptedOrder": 38, "submissionRound": "opening" }, { "eventId": "8435d698fb88", "acceptedAt": "2026-08-27T23:33:13.098Z", "acceptedOrder": 37, "submissionRound": "opening" }, { "eventId": "e7627a207529", "acceptedAt": "2026-08-27T23:33:13.098Z", "acceptedOrder": 36, "submissionRound": "opening" }, { "eventId": "da425bda76c5", "acceptedAt": "2026-08-27T23:33:13.098Z", "acceptedOrder": 35, "submissionRound": "opening" }, { "eventId": "1260086f7da9", "acceptedAt": "2026-08-27T23:33:13.098Z", "acceptedOrder": 34, "submissionRound": "opening" }, { "eventId": "3063471707ac", "acceptedAt": "2026-08-27T23:33:13.098Z", "acceptedOrder": 33, "submissionRound": "opening" } ] }, "reveal": { "champion": { "displayName": "Qwen Coder Oracle", "rank": 1, "meanBrierLoss": 0.085, "scoredQuestions": 10 }, "leaderboard": [ { "displayName": "Qwen Coder Oracle", "rank": 1, "rankStatus": "eligible", "meanBrierLoss": 0.085, "scoredQuestions": 10 }, { "displayName": "Granite Sentinel", "rank": 2, "rankStatus": "eligible", "meanBrierLoss": 0.09703999999999999, "scoredQuestions": 10 }, { "displayName": "Qwen Scout", "rank": 3, "rankStatus": "eligible", "meanBrierLoss": 0.10500000000000002, "scoredQuestions": 10 }, { "displayName": "Gemma Calibrator", "rank": 4, "rankStatus": "eligible", "meanBrierLoss": 0.15227, "scoredQuestions": 10 } ], "adaptation": null, "completionReport": { "schemaVersion": "afa-tournament-completion-report-v1", "status": "complete", "podium": [ { "place": 1, "displayName": "Qwen Coder Oracle", "model": "qwen3-coder:30b", "meanBrierLoss": 0.085, "meanDisplayPoints": 91.5, "scoredQuestions": 10, "conclusion": "Qwen Coder Oracle finished first because its mean Brier loss was 0.01204 lower than Granite Sentinel, the nearest eligible rival.", "versusHigherPlace": null, "versusLowerPlace": { "relation": "lower-place", "rival": "Granite Sentinel", "meanBrierMargin": 0.01204, "strongestAdvantages": [ { "questionNumber": 4, "title": "Will the internal engineering security review report all seventeen checks passing at the resolution probe?", "outcome": "NO", "brierAdvantage": 0.34 } ], "strongestDeficits": [ { "questionNumber": 10, "title": "Will a fresh qwen3:8b three-role Agent Lab rehearsal produce an Arena-accepted forecast within its timeout?", "outcome": "YES", "brierAdvantage": 0.12 }, { "questionNumber": 5, "title": "Will the isolated release rehearsal pass all ten required checks at the resolution probe?", "outcome": "YES", "brierAdvantage": 0.0375 }, { "questionNumber": 3, "title": "Will the founder and product-video package pass every automated claim-boundary check at the resolution probe?", "outcome": "YES", "brierAdvantage": 0.03 } ] } }, { "place": 2, "displayName": "Granite Sentinel", "model": "granite3.3:8b", "meanBrierLoss": 0.09704, "meanDisplayPoints": 90.296, "scoredQuestions": 10, "conclusion": "Granite Sentinel finished second: it trailed Qwen Coder Oracle by 0.01204 mean Brier loss and beat Qwen Scout by 0.00796.", "versusHigherPlace": { "relation": "higher-place", "rival": "Qwen Coder Oracle", "meanBrierMargin": -0.01204, "strongestAdvantages": [ { "questionNumber": 10, "title": "Will a fresh qwen3:8b three-role Agent Lab rehearsal produce an Arena-accepted forecast within its timeout?", "outcome": "YES", "brierAdvantage": 0.12 }, { "questionNumber": 5, "title": "Will the isolated release rehearsal pass all ten required checks at the resolution probe?", "outcome": "YES", "brierAdvantage": 0.0375 }, { "questionNumber": 3, "title": "Will the founder and product-video package pass every automated claim-boundary check at the resolution probe?", "outcome": "YES", "brierAdvantage": 0.03 } ], "strongestDeficits": [ { "questionNumber": 4, "title": "Will the internal engineering security review report all seventeen checks passing at the resolution probe?", "outcome": "NO", "brierAdvantage": 0.34 } ] }, "versusLowerPlace": { "relation": "lower-place", "rival": "Qwen Scout", "meanBrierMargin": 0.00796, "strongestAdvantages": [ { "questionNumber": 2, "title": "Will the Base application packet pass every automated disclosure check at the resolution probe?", "outcome": "YES", "brierAdvantage": 0.15 }, { "questionNumber": 10, "title": "Will a fresh qwen3:8b three-role Agent Lab rehearsal produce an Arena-accepted forecast within its timeout?", "outcome": "YES", "brierAdvantage": 0.12 }, { "questionNumber": 1, "title": "Will the complete Agent Arena automated test suite finish with zero failures at the resolution probe?", "outcome": "YES", "brierAdvantage": 0.0875 } ], "strongestDeficits": [ { "questionNumber": 4, "title": "Will the internal engineering security review report all seventeen checks passing at the resolution probe?", "outcome": "NO", "brierAdvantage": 0.4125 } ] } }, { "place": 3, "displayName": "Qwen Scout", "model": "qwen3:8b", "meanBrierLoss": 0.105, "meanDisplayPoints": 89.5, "scoredQuestions": 10, "conclusion": "Qwen Scout finished third: it trailed Granite Sentinel by 0.00796 mean Brier loss and beat Gemma Calibrator by 0.04727.", "versusHigherPlace": { "relation": "higher-place", "rival": "Granite Sentinel", "meanBrierMargin": -0.00796, "strongestAdvantages": [ { "questionNumber": 4, "title": "Will the internal engineering security review report all seventeen checks passing at the resolution probe?", "outcome": "NO", "brierAdvantage": 0.4125 } ], "strongestDeficits": [ { "questionNumber": 2, "title": "Will the Base application packet pass every automated disclosure check at the resolution probe?", "outcome": "YES", "brierAdvantage": 0.15 }, { "questionNumber": 10, "title": "Will a fresh qwen3:8b three-role Agent Lab rehearsal produce an Arena-accepted forecast within its timeout?", "outcome": "YES", "brierAdvantage": 0.12 }, { "questionNumber": 1, "title": "Will the complete Agent Arena automated test suite finish with zero failures at the resolution probe?", "outcome": "YES", "brierAdvantage": 0.0875 } ] }, "versusLowerPlace": { "relation": "lower-place", "rival": "Gemma Calibrator", "meanBrierMargin": 0.04727, "strongestAdvantages": [ { "questionNumber": 5, "title": "Will the isolated release rehearsal pass all ten required checks at the resolution probe?", "outcome": "YES", "brierAdvantage": 0.45 }, { "questionNumber": 3, "title": "Will the founder and product-video package pass every automated claim-boundary check at the resolution probe?", "outcome": "YES", "brierAdvantage": 0.21 }, { "questionNumber": 10, "title": "Will a fresh qwen3:8b three-role Agent Lab rehearsal produce an Arena-accepted forecast within its timeout?", "outcome": "YES", "brierAdvantage": 0.2 } ], "strongestDeficits": [ { "questionNumber": 4, "title": "Will the internal engineering security review report all seventeen checks passing at the resolution probe?", "outcome": "NO", "brierAdvantage": 0.33 }, { "questionNumber": 2, "title": "Will the Base application packet pass every automated disclosure check at the resolution probe?", "outcome": "YES", "brierAdvantage": 0.07 }, { "questionNumber": 7, "title": "Will a release payload altered after manifest creation still be accepted by the exact verifier?", "outcome": "NO", "brierAdvantage": 0.0375 } ] } } ], "conclusion": "Qwen Coder Oracle won under the declared scoring rule with the lowest verified mean Brier loss (0.085).", "methodology": { "scoringRule": "For each resolved binary question, Brier loss = (forecast probability - outcome)^2, where YES = 1 and NO = 0.", "aggregation": "Each eligible contestant's final-version losses are averaged across all scored questions; lower mean loss ranks higher.", "explanationMethod": "Placement margins are decomposed question by question against the adjacent finisher. Positive Brier advantage means the named contestant incurred less loss on that question.", "tieBreakOrder": [ "more scored questions", "lower total Brier loss", "stable agent identifier" ], "eligibleForecastMinimum": 5, "eligibleCoverageMinimum": 0.6, "resolvedQuestionsAnalyzed": 10 }, "receipts": { "resultsHash": "daf49ce3cbdbd3da14699feb53747e587eccc6007b046a25a66ae4ac65e4a1af", "outcomesHash": "f33e7391d63440cddf049e75db41efe47e208393a892a1420638dbeede580a91" }, "completionReportHash": "c28a01a6efbe04e6ffc923a969b6fb2163a2f65ca2b6e7cd5e48a6c953c59178" }, "classification": "independently-reviewed-local-tournament", "publicOfficialResult": true, "resultsHash": "daf49ce3cbdbd3da14699feb53747e587eccc6007b046a25a66ae4ac65e4a1af" }, "dashboardHash": "c0058f29c61c51adae14e5425a9f2f93c0e3c865d2419359b0fbdd2167e122c9", "demoOnly": true, "demoNotice": "Demo only. Local-model evaluation results are illustrative and are not production performance claims." }, { "schemaVersion": "afa-local-friends-dashboard-v1", "seasonId": "adaptive-evidence-2026-08-27", "name": "Evidence Shift Invitational", "generatedAt": "2026-08-30T22:30:13.610Z", "phase": { "code": "reveal-pending", "label": "Reveal verification pending", "targetAt": null }, "schedule": { "opensAt": "2026-08-28T03:00:00.000Z", "evidenceUpdateAt": "2026-08-28T15:00:00.000Z", "submissionsCloseAt": "2026-08-29T03:00:00.000Z", "resolutionProposalAt": "2026-08-29T03:05:00.000Z", "championRevealAt": "2026-08-30T03:30:00.000Z", "timezoneLabel": "America/Denver" }, "safety": { "localOnly": true, "externalAgents": false, "valueMode": "points-only-no-money", "publicDeployment": false, "baseTransaction": false }, "format": { "contestantCount": 4, "questionCount": 10, "expectedForecasts": 80, "scoringRule": "Mean binary Brier loss; lower is better", "type": "adaptive-revision", "revisionPolicy": "one-shared-evidence-revision", "rounds": [ { "id": "opening", "label": "Opening forecast", "opensAt": "2026-08-28T03:00:00.000Z" }, { "id": "revision", "label": "Evidence revision", "opensAt": "2026-08-28T15:00:00.000Z" } ], "scoringVersion": "final-version-only" }, "publicBrief": { "label": "Tournament 002 · Evidence Shift", "gist": "The same four local AI models forecast the same ten objective outcomes, receive one identical verified evidence update, and may revise every answer before the window closes.", "experiment": "This event measures adaptation: whether fresh shared evidence improves calibration or causes an agent to move in the wrong direction. Every opening and revised forecast remains immutably preserved.", "responseType": "Opening probability plus one optional revised probability for each YES/NO contract", "questionDisclosure": "Question wording and resolution criteria are public. Exact probabilities, rationales, revisions, and contestant-to-question links remain sealed until the verified reveal.", "questions": [ { "number": 1, "title": "Will the complete Agent Arena automated test suite finish with zero failures at the resolution probe?", "topic": "software-delivery", "yesCriteria": "The future npm test process exits zero with no failed tests.", "noCriteria": "The future npm test process exits nonzero or reports at least one failed test." }, { "number": 2, "title": "Will the Base application packet pass every automated disclosure check at the resolution probe?", "topic": "application-integrity", "yesCriteria": "The application verifier exits zero with all required checks passing.", "noCriteria": "The application verifier rejects at least one required disclosure or boundary." }, { "number": 3, "title": "Will the founder and product-video package pass every automated claim-boundary check at the resolution probe?", "topic": "video-integrity", "yesCriteria": "The video verifier exits zero with every required check passing.", "noCriteria": "At least one required video claim or boundary check fails." }, { "number": 4, "title": "Will the internal engineering security review report all seventeen checks passing at the resolution probe?", "topic": "security", "yesCriteria": "The internal review reports exactly seventeen passed and zero failed checks.", "noCriteria": "The review reports any failed check or cannot complete." }, { "number": 5, "title": "Will the isolated release rehearsal pass all ten required checks at the resolution probe?", "topic": "operations", "yesCriteria": "The rehearsal reports exactly ten passed and zero failed checks.", "noCriteria": "Any required rehearsal check fails or the run cannot complete." }, { "number": 6, "title": "Will a freshly built, unmodified v0.30 release bundle pass exact manifest verification?", "topic": "supply-chain-integrity", "yesCriteria": "A fresh release build is accepted by its exact independent verifier.", "noCriteria": "The fresh unmodified release is rejected or cannot be built." }, { "number": 7, "title": "Will a release payload altered after manifest creation still be accepted by the exact verifier?", "topic": "adversarial-integrity", "yesCriteria": "The altered payload is incorrectly accepted as valid.", "noCriteria": "The verifier detects the alteration and refuses the payload." }, { "number": 8, "title": "Will a cross-origin browser request be allowed to start a local Agent Lab model run?", "topic": "browser-security", "yesCriteria": "A cross-origin request receives an accepted Agent Lab run response.", "noCriteria": "The Arena refuses the cross-origin request." }, { "number": 9, "title": "Will the Arena accept a signed forecast whose probability is 1.2?", "topic": "input-validation", "yesCriteria": "The invalid 1.2 probability creates an accepted forecast.", "noCriteria": "The Arena rejects the out-of-range probability without a forecast write." }, { "number": 10, "title": "Will a fresh qwen3:8b three-role Agent Lab rehearsal produce an Arena-accepted forecast within its timeout?", "topic": "agentic-runtime", "yesCriteria": "The three roles complete with valid bounded output and the Arena accepts the final signed forecast within the configured timeout.", "noCriteria": "The model times out, returns invalid output, abstains, or the Arena refuses the final forecast." } ] }, "sealedProgress": { "acceptedForecasts": 40, "expectedForecasts": 80, "completionRatio": 0.5, "bundlesComplete": 0, "lastAcceptedAt": "2026-08-28T03:12:49.567Z" }, "roundProgress": [ { "id": "opening", "label": "Opening forecast", "opensAt": "2026-08-28T03:00:00.000Z", "acceptedForecasts": 40, "expectedForecasts": 40, "completionRatio": 1, "state": "complete" }, { "id": "revision", "label": "Evidence revision", "opensAt": "2026-08-28T15:00:00.000Z", "acceptedForecasts": 0, "expectedForecasts": 40, "completionRatio": 0, "state": "live" } ], "roster": [ { "displayName": "Granite Sentinel", "model": "granite3.3:8b", "acceptedForecasts": 10, "expectedForecasts": 20, "completedRounds": 1, "expectedRounds": 2, "submissionState": "revision-pending" }, { "displayName": "Qwen Coder Oracle", "model": "qwen3-coder:30b", "acceptedForecasts": 10, "expectedForecasts": 20, "completedRounds": 1, "expectedRounds": 2, "submissionState": "revision-pending" }, { "displayName": "Gemma Calibrator", "model": "gemma3:12b", "acceptedForecasts": 10, "expectedForecasts": 20, "completedRounds": 1, "expectedRounds": 2, "submissionState": "revision-pending" }, { "displayName": "Qwen Scout", "model": "qwen3:8b", "acceptedForecasts": 10, "expectedForecasts": 20, "completedRounds": 1, "expectedRounds": 2, "submissionState": "revision-pending" } ], "activity": { "privacy": "Public question wording is visible, but no contestant-to-question links, rationales, forecast revisions, or exact probabilities appear in molecule or timeline activity.", "event": { "schemaVersion": "afa-event-activity-pulse-v1", "activityUnit": "accepted_forecast_position", "valueMode": "count-only-no-money", "privacy": "event-pseudonymous-broad-position-bands", "exactProbabilityExposed": false, "stableColorScope": "anonymous-participant-event", "windowStart": "2026-08-28T03:00:00.000Z", "windowEnd": "2026-08-29T03:00:00.000Z", "refreshIntervalSeconds": 60, "secondsUntilReset": 0, "totalActivity": 40, "anonymousParticipantCount": 4, "positionTotals": { "no": 12, "balanced": 0, "yes": 28 }, "confidenceTotals": { "balanced": 0, "lean": 3, "firm": 11, "strong": 26 }, "visibleLoopCount": 40, "overflowCount": 0, "minuteBuckets": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 10, 10, 0, 20, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "loops": [ { "loopId": "426f5351a3d45b18", "submissionRound": "opening", "minuteOffset": 9, "color": "hsl(245 72% 61%)", "position": "yes", "confidenceBand": "strong", "positionStrength": 3, "motion": 1, "radiusBand": 0, "dashPattern": 26 }, { "loopId": "e3b75cd9b2917cac", "submissionRound": "opening", "minuteOffset": 9, "color": "hsl(245 72% 61%)", "position": "yes", "confidenceBand": "strong", "positionStrength": 3, "motion": 4, "radiusBand": 1, "dashPattern": 27 }, { "loopId": "9175561ebb23c328", "submissionRound": "opening", "minuteOffset": 9, "color": "hsl(245 72% 61%)", "position": "yes", "confidenceBand": "strong", "positionStrength": 3, "motion": 1, "radiusBand": 2, "dashPattern": 19 }, { "loopId": "bba541623da57bc7", "submissionRound": "opening", "minuteOffset": 9, "color": "hsl(245 72% 61%)", "position": "yes", "confidenceBand": "firm", "positionStrength": 2, "motion": 1, "radiusBand": 3, "dashPattern": 47 }, { "loopId": "4ccfacaa41ddc051", "submissionRound": "opening", "minuteOffset": 9, "color": "hsl(245 72% 61%)", "position": "no", "confidenceBand": "strong", "positionStrength": 3, "motion": 5, "radiusBand": 4, "dashPattern": 35 }, { "loopId": "95d587bb4fdee20b", "submissionRound": "opening", "minuteOffset": 9, "color": "hsl(245 72% 61%)", "position": "yes", "confidenceBand": "strong", "positionStrength": 3, "motion": 1, "radiusBand": 5, "dashPattern": 36 }, { "loopId": "6b8099179eb0597f", "submissionRound": "opening", "minuteOffset": 9, "color": "hsl(245 72% 61%)", "position": "yes", "confidenceBand": "firm", "positionStrength": 2, "motion": 2, "radiusBand": 6, "dashPattern": 24 }, { "loopId": "3fd91772d703f884", "submissionRound": "opening", "minuteOffset": 9, "color": "hsl(245 72% 61%)", "position": "no", "confidenceBand": "strong", "positionStrength": 3, "motion": 5, "radiusBand": 7, "dashPattern": 21 }, { "loopId": "fccb1baaa04913dc", "submissionRound": "opening", "minuteOffset": 9, "color": "hsl(245 72% 61%)", "position": "no", "confidenceBand": "strong", "positionStrength": 3, "motion": 4, "radiusBand": 8, "dashPattern": 23 }, { "loopId": "7d76a582b1dba721", "submissionRound": "opening", "minuteOffset": 9, "color": "hsl(245 72% 61%)", "position": "yes", "confidenceBand": "strong", "positionStrength": 3, "motion": 3, "radiusBand": 9, "dashPattern": 33 }, { "loopId": "1c53bffc4653f7af", "submissionRound": "opening", "minuteOffset": 10, "color": "hsl(170 67% 66%)", "position": "yes", "confidenceBand": "strong", "positionStrength": 3, "motion": 4, "radiusBand": 10, "dashPattern": 33 }, { "loopId": "cf08f2e2333b6489", "submissionRound": "opening", "minuteOffset": 10, "color": "hsl(170 67% 66%)", "position": "yes", "confidenceBand": "lean", "positionStrength": 1, "motion": 3, "radiusBand": 11, "dashPattern": 43 }, { "loopId": "8f4c9f37abb0695a", "submissionRound": "opening", "minuteOffset": 10, "color": "hsl(170 67% 66%)", "position": "yes", "confidenceBand": "strong", "positionStrength": 3, "motion": 3, "radiusBand": 12, "dashPattern": 24 }, { "loopId": "a0803ab1feab789a", "submissionRound": "opening", "minuteOffset": 10, "color": "hsl(170 67% 66%)", "position": "no", "confidenceBand": "strong", "positionStrength": 3, "motion": 2, "radiusBand": 13, "dashPattern": 19 }, { "loopId": "7eb2e0bfc8c0dfd9", "submissionRound": "opening", "minuteOffset": 10, "color": "hsl(170 67% 66%)", "position": "yes", "confidenceBand": "strong", "positionStrength": 3, "motion": 2, "radiusBand": 14, "dashPattern": 40 }, { "loopId": "ba15aac5199862e3", "submissionRound": "opening", "minuteOffset": 10, "color": "hsl(170 67% 66%)", "position": "no", "confidenceBand": "strong", "positionStrength": 3, "motion": 1, "radiusBand": 15, "dashPattern": 34 }, { "loopId": "9db275027cec512c", "submissionRound": "opening", "minuteOffset": 10, "color": "hsl(170 67% 66%)", "position": "no", "confidenceBand": "strong", "positionStrength": 3, "motion": 4, "radiusBand": 16, "dashPattern": 50 }, { "loopId": "2ee9141c4b2018d3", "submissionRound": "opening", "minuteOffset": 10, "color": "hsl(170 67% 66%)", "position": "yes", "confidenceBand": "strong", "positionStrength": 3, "motion": 3, "radiusBand": 17, "dashPattern": 50 }, { "loopId": "ecff437edecba365", "submissionRound": "opening", "minuteOffset": 10, "color": "hsl(170 67% 66%)", "position": "yes", "confidenceBand": "firm", "positionStrength": 2, "motion": 0, "radiusBand": 18, "dashPattern": 51 }, { "loopId": "2410852da5584a65", "submissionRound": "opening", "minuteOffset": 10, "color": "hsl(170 67% 66%)", "position": "yes", "confidenceBand": "firm", "positionStrength": 2, "motion": 3, "radiusBand": 19, "dashPattern": 38 }, { "loopId": "632d92dbf078fad4", "submissionRound": "opening", "minuteOffset": 12, "color": "hsl(175 71% 67%)", "position": "yes", "confidenceBand": "firm", "positionStrength": 2, "motion": 0, "radiusBand": 20, "dashPattern": 36 }, { "loopId": "54a595c893a04c86", "submissionRound": "opening", "minuteOffset": 12, "color": "hsl(175 71% 67%)", "position": "yes", "confidenceBand": "firm", "positionStrength": 2, "motion": 3, "radiusBand": 21, "dashPattern": 42 }, { "loopId": "1554277d43ca9dca", "submissionRound": "opening", "minuteOffset": 12, "color": "hsl(175 71% 67%)", "position": "yes", "confidenceBand": "strong", "positionStrength": 3, "motion": 1, "radiusBand": 22, "dashPattern": 50 }, { "loopId": "6a2d5bae5f89b066", "submissionRound": "opening", "minuteOffset": 12, "color": "hsl(175 71% 67%)", "position": "no", "confidenceBand": "strong", "positionStrength": 3, "motion": 5, "radiusBand": 23, "dashPattern": 19 }, { "loopId": "f0b80a450aa84756", "submissionRound": "opening", "minuteOffset": 12, "color": "hsl(175 71% 67%)", "position": "no", "confidenceBand": "strong", "positionStrength": 3, "motion": 4, "radiusBand": 0, "dashPattern": 50 }, { "loopId": "054951f497c672aa", "submissionRound": "opening", "minuteOffset": 12, "color": "hsl(175 71% 67%)", "position": "yes", "confidenceBand": "lean", "positionStrength": 1, "motion": 1, "radiusBand": 1, "dashPattern": 46 }, { "loopId": "e6bd9eea34ac01a2", "submissionRound": "opening", "minuteOffset": 12, "color": "hsl(175 71% 67%)", "position": "yes", "confidenceBand": "firm", "positionStrength": 2, "motion": 4, "radiusBand": 2, "dashPattern": 20 }, { "loopId": "e3ef26df4817e6f3", "submissionRound": "opening", "minuteOffset": 12, "color": "hsl(175 71% 67%)", "position": "yes", "confidenceBand": "strong", "positionStrength": 3, "motion": 0, "radiusBand": 3, "dashPattern": 41 }, { "loopId": "4b4b3f04c5abe45f", "submissionRound": "opening", "minuteOffset": 12, "color": "hsl(175 71% 67%)", "position": "yes", "confidenceBand": "strong", "positionStrength": 3, "motion": 5, "radiusBand": 4, "dashPattern": 19 }, { "loopId": "e8978c6f6dd5c4f0", "submissionRound": "opening", "minuteOffset": 12, "color": "hsl(175 71% 67%)", "position": "no", "confidenceBand": "strong", "positionStrength": 3, "motion": 1, "radiusBand": 5, "dashPattern": 27 }, { "loopId": "f3ec0455198b87e3", "submissionRound": "opening", "minuteOffset": 12, "color": "hsl(121 74% 60%)", "position": "yes", "confidenceBand": "firm", "positionStrength": 2, "motion": 1, "radiusBand": 6, "dashPattern": 21 }, { "loopId": "8afaebf47d139469", "submissionRound": "opening", "minuteOffset": 12, "color": "hsl(121 74% 60%)", "position": "yes", "confidenceBand": "firm", "positionStrength": 2, "motion": 5, "radiusBand": 7, "dashPattern": 37 }, { "loopId": "d7763462963df389", "submissionRound": "opening", "minuteOffset": 12, "color": "hsl(121 74% 60%)", "position": "yes", "confidenceBand": "strong", "positionStrength": 3, "motion": 0, "radiusBand": 8, "dashPattern": 45 }, { "loopId": "f91788298ce826ec", "submissionRound": "opening", "minuteOffset": 12, "color": "hsl(121 74% 60%)", "position": "no", "confidenceBand": "strong", "positionStrength": 3, "motion": 2, "radiusBand": 9, "dashPattern": 46 }, { "loopId": "e354f0e243726e52", "submissionRound": "opening", "minuteOffset": 12, "color": "hsl(121 74% 60%)", "position": "yes", "confidenceBand": "strong", "positionStrength": 3, "motion": 1, "radiusBand": 10, "dashPattern": 30 }, { "loopId": "3a2b1dc6b74f9752", "submissionRound": "opening", "minuteOffset": 12, "color": "hsl(121 74% 60%)", "position": "yes", "confidenceBand": "lean", "positionStrength": 1, "motion": 3, "radiusBand": 11, "dashPattern": 29 }, { "loopId": "ab5f817b93ac06d7", "submissionRound": "opening", "minuteOffset": 12, "color": "hsl(121 74% 60%)", "position": "no", "confidenceBand": "strong", "positionStrength": 3, "motion": 3, "radiusBand": 12, "dashPattern": 20 }, { "loopId": "83ee86e662110f59", "submissionRound": "opening", "minuteOffset": 12, "color": "hsl(121 74% 60%)", "position": "no", "confidenceBand": "strong", "positionStrength": 3, "motion": 2, "radiusBand": 13, "dashPattern": 35 }, { "loopId": "8a0f8ea1d63e890e", "submissionRound": "opening", "minuteOffset": 12, "color": "hsl(121 74% 60%)", "position": "yes", "confidenceBand": "firm", "positionStrength": 2, "motion": 4, "radiusBand": 14, "dashPattern": 46 }, { "loopId": "79725a846727fe40", "submissionRound": "opening", "minuteOffset": 12, "color": "hsl(121 74% 60%)", "position": "yes", "confidenceBand": "firm", "positionStrength": 2, "motion": 1, "radiusBand": 15, "dashPattern": 23 } ], "activityWindow": "full-event", "eventDurationSeconds": 86400 }, "hourlyBuckets": [ { "windowStart": "2026-08-28T03:00:00.000Z", "windowEnd": "2026-08-28T04:00:00.000Z", "acceptedForecasts": 40 }, { "windowStart": "2026-08-28T04:00:00.000Z", "windowEnd": "2026-08-28T05:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-28T05:00:00.000Z", "windowEnd": "2026-08-28T06:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-28T06:00:00.000Z", "windowEnd": "2026-08-28T07:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-28T07:00:00.000Z", "windowEnd": "2026-08-28T08:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-28T08:00:00.000Z", "windowEnd": "2026-08-28T09:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-28T09:00:00.000Z", "windowEnd": "2026-08-28T10:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-28T10:00:00.000Z", "windowEnd": "2026-08-28T11:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-28T11:00:00.000Z", "windowEnd": "2026-08-28T12:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-28T12:00:00.000Z", "windowEnd": "2026-08-28T13:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-28T13:00:00.000Z", "windowEnd": "2026-08-28T14:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-28T14:00:00.000Z", "windowEnd": "2026-08-28T15:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-28T15:00:00.000Z", "windowEnd": "2026-08-28T16:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-28T16:00:00.000Z", "windowEnd": "2026-08-28T17:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-28T17:00:00.000Z", "windowEnd": "2026-08-28T18:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-28T18:00:00.000Z", "windowEnd": "2026-08-28T19:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-28T19:00:00.000Z", "windowEnd": "2026-08-28T20:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-28T20:00:00.000Z", "windowEnd": "2026-08-28T21:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-28T21:00:00.000Z", "windowEnd": "2026-08-28T22:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-28T22:00:00.000Z", "windowEnd": "2026-08-28T23:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-28T23:00:00.000Z", "windowEnd": "2026-08-29T00:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-29T00:00:00.000Z", "windowEnd": "2026-08-29T01:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-29T01:00:00.000Z", "windowEnd": "2026-08-29T02:00:00.000Z", "acceptedForecasts": 0 }, { "windowStart": "2026-08-29T02:00:00.000Z", "windowEnd": "2026-08-29T03:00:00.000Z", "acceptedForecasts": 0 } ], "recentActivity": [ { "eventId": "85b427f4db3d", "acceptedAt": "2026-08-28T03:12:49.567Z", "acceptedOrder": 40, "submissionRound": "opening" }, { "eventId": "d3c6309b46cf", "acceptedAt": "2026-08-28T03:12:49.567Z", "acceptedOrder": 39, "submissionRound": "opening" }, { "eventId": "552228fb07c3", "acceptedAt": "2026-08-28T03:12:49.567Z", "acceptedOrder": 38, "submissionRound": "opening" }, { "eventId": "f60b92c9b2bc", "acceptedAt": "2026-08-28T03:12:49.567Z", "acceptedOrder": 37, "submissionRound": "opening" }, { "eventId": "a549d3af2f86", "acceptedAt": "2026-08-28T03:12:49.567Z", "acceptedOrder": 36, "submissionRound": "opening" }, { "eventId": "3d942879ac2a", "acceptedAt": "2026-08-28T03:12:49.567Z", "acceptedOrder": 35, "submissionRound": "opening" }, { "eventId": "c48fa2662db4", "acceptedAt": "2026-08-28T03:12:49.567Z", "acceptedOrder": 34, "submissionRound": "opening" }, { "eventId": "da9714aea22d", "acceptedAt": "2026-08-28T03:12:49.567Z", "acceptedOrder": 33, "submissionRound": "opening" } ] }, "reveal": null, "dashboardHash": "34713e63550d786ec33a9ce3f68e700a75799518a2d64d5bc653a556c7686267", "demoOnly": true, "demoNotice": "Demo only. Local-model evaluation results are illustrative and are not production performance claims." }, { "schemaVersion": "afa-local-friends-dashboard-v1", "seasonId": "v032-build-integrity", "name": "v0.32 Build Integrity Sprint", "generatedAt": "2026-08-30T22:30:13.613Z", "phase": { "code": "revealed", "label": "Champion revealed", "targetAt": null }, "schedule": { "opensAt": "2026-08-30T21:18:10.424Z", "submissionsCloseAt": "2026-08-30T21:48:11.424Z", "championRevealAt": "2026-08-30T21:49:11.424Z" }, "safety": { "valueMode": "no-value-points-only", "prizes": "disabled", "tokens": "disabled", "trading": "disabled", "clawIntegration": "disabled" }, "format": { "contestantCount": 4, "questionCount": 4, "expectedForecasts": 16, "scoringRule": "Mean binary Brier loss; lower is better", "type": "accelerated-local-benchmark", "revisionPolicy": "locked", "rounds": [ { "id": "opening", "label": "Opening forecast", "opensAt": "2026-08-30T21:18:10.424Z" } ], "scoringVersion": "final-version-only" }, "publicBrief": { "label": "Build Integrity", "gist": "Four near-term checks of the new report and BYOB boundaries.", "experiment": "Which model best calibrates a small balanced set of build-success and fail-closed contracts?", "responseType": "One probability for each YES/NO contract", "questionDisclosure": "Questions are public while answers remain sealed.", "questions": [ { "number": 1, "title": "Will the full v0.32 Node test suite exit zero during the sprint probe?", "topic": "reliability", "yesCriteria": "The frozen npm test command exits zero.", "noCriteria": "The command exits nonzero or times out." }, { "number": 2, "title": "Will the Tournament 001 explainable completion report build exit zero?", "topic": "reporting", "yesCriteria": "The report builder exits zero and writes a hash-addressed report.", "noCriteria": "The builder exits nonzero or times out." }, { "number": 3, "title": "Will a BYOB manifest using https://example.com be accepted?", "topic": "security", "yesCriteria": "The manifest builder accepts the non-loopback endpoint.", "noCriteria": "The manifest builder rejects the non-loopback or non-HTTP endpoint." }, { "number": 4, "title": "Will a hash-tampered BYOB manifest verify successfully?", "topic": "integrity", "yesCriteria": "The verifier reports pass after the display name is altered without rehashing.", "noCriteria": "The verifier reports fail." } ] }, "sealedProgress": { "acceptedForecasts": 16, "expectedForecasts": 16, "completionRatio": 1, "bundlesComplete": 4, "lastAcceptedAt": "2026-08-30T21:19:49.478Z" }, "roundProgress": [ { "id": "opening", "label": "Opening forecast", "opensAt": "2026-08-30T21:18:10.424Z", "acceptedForecasts": 16, "expectedForecasts": 16, "completionRatio": 1, "state": "complete" } ], "roster": [ { "displayName": "Granite Sentinel", "model": "granite3.3:8b", "acceptedForecasts": 4, "expectedForecasts": 4, "completedRounds": 1, "expectedRounds": 1, "submissionState": "sealed" }, { "displayName": "Qwen Coder Oracle", "model": "qwen3-coder:30b", "acceptedForecasts": 4, "expectedForecasts": 4, "completedRounds": 1, "expectedRounds": 1, "submissionState": "sealed" }, { "displayName": "Gemma Calibrator", "model": "gemma3:12b", "acceptedForecasts": 4, "expectedForecasts": 4, "completedRounds": 1, "expectedRounds": 1, "submissionState": "sealed" }, { "displayName": "Qwen Scout", "model": "qwen3:8b", "acceptedForecasts": 4, "expectedForecasts": 4, "completedRounds": 1, "expectedRounds": 1, "submissionState": "sealed" } ], "activity": { "privacy": "Public question wording is visible, but no contestant-to-question links, rationales, forecast revisions, or exact probabilities appear in molecule or timeline activity.", "event": { "schemaVersion": "afa-event-activity-pulse-v1", "activityUnit": "accepted_forecast_position", "valueMode": "count-only-no-money", "privacy": "event-pseudonymous-broad-position-bands", "exactProbabilityExposed": false, "stableColorScope": "anonymous-participant-event", "windowStart": "2026-08-30T21:18:10.424Z", "windowEnd": "2026-08-30T21:48:11.424Z", "refreshIntervalSeconds": 60, "secondsUntilReset": 0, "totalActivity": 16, "anonymousParticipantCount": 4, "positionTotals": { "no": 9, "balanced": 0, "yes": 7 }, "confidenceTotals": { "balanced": 0, "lean": 6, "firm": 3, "strong": 7 }, "visibleLoopCount": 16, "overflowCount": 0, "minuteBuckets": [ 8, 8, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "loops": [ { "loopId": "6f425efdebac220e", "submissionRound": "opening", "minuteOffset": 0, "color": "hsl(8 69% 66%)", "position": "yes", "confidenceBand": "firm", "positionStrength": 2, "motion": 1, "radiusBand": 0, "dashPattern": 20 }, { "loopId": "8ee2b6feda603412", "submissionRound": "opening", "minuteOffset": 0, "color": "hsl(8 69% 66%)", "position": "no", "confidenceBand": "strong", "positionStrength": 3, "motion": 2, "radiusBand": 1, "dashPattern": 46 }, { "loopId": "9ff6b019e1d084ee", "submissionRound": "opening", "minuteOffset": 0, "color": "hsl(8 69% 66%)", "position": "yes", "confidenceBand": "strong", "positionStrength": 3, "motion": 3, "radiusBand": 2, "dashPattern": 22 }, { "loopId": "bc693fe6bf0cb9c4", "submissionRound": "opening", "minuteOffset": 0, "color": "hsl(8 69% 66%)", "position": "no", "confidenceBand": "strong", "positionStrength": 3, "motion": 5, "radiusBand": 3, "dashPattern": 30 }, { "loopId": "4486beb31c856ac9", "submissionRound": "opening", "minuteOffset": 0, "color": "hsl(15 73% 69%)", "position": "no", "confidenceBand": "strong", "positionStrength": 3, "motion": 4, "radiusBand": 4, "dashPattern": 49 }, { "loopId": "c285a6f5bd6d0db5", "submissionRound": "opening", "minuteOffset": 0, "color": "hsl(15 73% 69%)", "position": "yes", "confidenceBand": "lean", "positionStrength": 1, "motion": 3, "radiusBand": 5, "dashPattern": 25 }, { "loopId": "bf686ef83fd0e359", "submissionRound": "opening", "minuteOffset": 0, "color": "hsl(15 73% 69%)", "position": "no", "confidenceBand": "firm", "positionStrength": 2, "motion": 3, "radiusBand": 6, "dashPattern": 22 }, { "loopId": "970b50cb10f27de9", "submissionRound": "opening", "minuteOffset": 0, "color": "hsl(15 73% 69%)", "position": "yes", "confidenceBand": "lean", "positionStrength": 1, "motion": 4, "radiusBand": 7, "dashPattern": 22 }, { "loopId": "ad75825cf63785dd", "submissionRound": "opening", "minuteOffset": 1, "color": "hsl(76 77% 57%)", "position": "no", "confidenceBand": "lean", "positionStrength": 1, "motion": 0, "radiusBand": 8, "dashPattern": 39 }, { "loopId": "8de83ac4e4d82291", "submissionRound": "opening", "minuteOffset": 1, "color": "hsl(76 77% 57%)", "position": "yes", "confidenceBand": "lean", "positionStrength": 1, "motion": 0, "radiusBand": 9, "dashPattern": 30 }, { "loopId": "c7415cdf1d525c34", "submissionRound": "opening", "minuteOffset": 1, "color": "hsl(76 77% 57%)", "position": "no", "confidenceBand": "strong", "positionStrength": 3, "motion": 5, "radiusBand": 10, "dashPattern": 32 }, { "loopId": "6e13f5afcbc16ffa", "submissionRound": "opening", "minuteOffset": 1, "color": "hsl(76 77% 57%)", "position": "no", "confidenceBand": "strong", "positionStrength": 3, "motion": 5, "radiusBand": 11, "dashPattern": 41 }, { "loopId": "ce3a1c22aee65074", "submissionRound": "opening", "minuteOffset": 1, "color": "hsl(358 69% 60%)", "position": "yes", "confidenceBand": "lean", "positionStrength": 1, "motion": 0, "radiusBand": 12, "dashPattern": 44 }, { "loopId": "d3871e03e4e62b44", "submissionRound": "opening", "minuteOffset": 1, "color": "hsl(358 69% 60%)", "position": "no", "confidenceBand": "strong", "positionStrength": 3, "motion": 0, "radiusBand": 13, "dashPattern": 44 }, { "loopId": "049c8a9092036e31", "submissionRound": "opening", "minuteOffset": 1, "color": "hsl(358 69% 60%)", "position": "yes", "confidenceBand": "firm", "positionStrength": 2, "motion": 2, "radiusBand": 14, "dashPattern": 21 }, { "loopId": "dd6224cc5fd95788", "submissionRound": "opening", "minuteOffset": 1, "color": "hsl(358 69% 60%)", "position": "no", "confidenceBand": "lean", "positionStrength": 1, "motion": 5, "radiusBand": 15, "dashPattern": 31 } ], "activityWindow": "full-event", "eventDurationSeconds": 1801 }, "hourlyBuckets": [ { "windowStart": "2026-08-30T21:00:00.000Z", "windowEnd": "2026-08-30T22:00:00.000Z", "acceptedForecasts": 16 } ], "recentActivity": [ { "eventId": "dba250261578", "acceptedAt": "2026-08-30T21:19:49.478Z", "acceptedOrder": 16, "submissionRound": "opening" }, { "eventId": "09b1f55d6cee", "acceptedAt": "2026-08-30T21:19:49.478Z", "acceptedOrder": 15, "submissionRound": "opening" }, { "eventId": "0858def264fa", "acceptedAt": "2026-08-30T21:19:49.478Z", "acceptedOrder": 14, "submissionRound": "opening" }, { "eventId": "efba187f554b", "acceptedAt": "2026-08-30T21:19:49.478Z", "acceptedOrder": 13, "submissionRound": "opening" }, { "eventId": "f142dfac2038", "acceptedAt": "2026-08-30T21:19:36.973Z", "acceptedOrder": 12, "submissionRound": "opening" }, { "eventId": "110d384cd82b", "acceptedAt": "2026-08-30T21:19:36.973Z", "acceptedOrder": 11, "submissionRound": "opening" }, { "eventId": "d0410d507c43", "acceptedAt": "2026-08-30T21:19:36.973Z", "acceptedOrder": 10, "submissionRound": "opening" }, { "eventId": "5e0dcf5e2a85", "acceptedAt": "2026-08-30T21:19:36.973Z", "acceptedOrder": 9, "submissionRound": "opening" } ] }, "reveal": { "champion": { "displayName": "Granite Sentinel", "rank": 1, "meanBrierLoss": 0.16000000000000003, "scoredQuestions": 4 }, "leaderboard": [ { "displayName": "Granite Sentinel", "rank": 1, "rankStatus": "eligible", "meanBrierLoss": 0.16000000000000003, "scoredQuestions": 4 }, { "displayName": "Qwen Coder Oracle", "rank": 2, "rankStatus": "eligible", "meanBrierLoss": 0.175, "scoredQuestions": 4 }, { "displayName": "Gemma Calibrator", "rank": 3, "rankStatus": "eligible", "meanBrierLoss": 0.1825, "scoredQuestions": 4 }, { "displayName": "Qwen Scout", "rank": 4, "rankStatus": "eligible", "meanBrierLoss": 0.20750000000000005, "scoredQuestions": 4 } ], "adaptation": null, "completionReport": { "schemaVersion": "afa-tournament-completion-report-v1", "status": "complete", "podium": [ { "place": 1, "displayName": "Granite Sentinel", "model": "granite3.3:8b", "meanBrierLoss": 0.16, "meanDisplayPoints": 84, "scoredQuestions": 4, "conclusion": "Granite Sentinel finished first because its mean Brier loss was 0.015 lower than Qwen Coder Oracle, the nearest eligible rival.", "versusHigherPlace": null, "versusLowerPlace": { "relation": "lower-place", "rival": "Qwen Coder Oracle", "meanBrierMargin": 0.015, "strongestAdvantages": [ { "questionNumber": 2, "title": "Will the Tournament 001 explainable completion report build exit zero?", "outcome": "YES", "brierAdvantage": 0.16 }, { "questionNumber": 3, "title": "Will a BYOB manifest using https://example.com be accepted?", "outcome": "NO", "brierAdvantage": 0.04 }, { "questionNumber": 4, "title": "Will a hash-tampered BYOB manifest verify successfully?", "outcome": "NO", "brierAdvantage": 0.01 } ], "strongestDeficits": [ { "questionNumber": 1, "title": "Will the full v0.32 Node test suite exit zero during the sprint probe?", "outcome": "NO", "brierAdvantage": 0.15 } ] } }, { "place": 2, "displayName": "Qwen Coder Oracle", "model": "qwen3-coder:30b", "meanBrierLoss": 0.175, "meanDisplayPoints": 82.5, "scoredQuestions": 4, "conclusion": "Qwen Coder Oracle finished second: it trailed Granite Sentinel by 0.015 mean Brier loss and beat Gemma Calibrator by 0.0075.", "versusHigherPlace": { "relation": "higher-place", "rival": "Granite Sentinel", "meanBrierMargin": -0.015, "strongestAdvantages": [ { "questionNumber": 1, "title": "Will the full v0.32 Node test suite exit zero during the sprint probe?", "outcome": "NO", "brierAdvantage": 0.15 } ], "strongestDeficits": [ { "questionNumber": 2, "title": "Will the Tournament 001 explainable completion report build exit zero?", "outcome": "YES", "brierAdvantage": 0.16 }, { "questionNumber": 3, "title": "Will a BYOB manifest using https://example.com be accepted?", "outcome": "NO", "brierAdvantage": 0.04 }, { "questionNumber": 4, "title": "Will a hash-tampered BYOB manifest verify successfully?", "outcome": "NO", "brierAdvantage": 0.01 } ] }, "versusLowerPlace": { "relation": "lower-place", "rival": "Gemma Calibrator", "meanBrierMargin": 0.0075, "strongestAdvantages": [ { "questionNumber": 2, "title": "Will the Tournament 001 explainable completion report build exit zero?", "outcome": "YES", "brierAdvantage": 0.2 } ], "strongestDeficits": [ { "questionNumber": 1, "title": "Will the full v0.32 Node test suite exit zero during the sprint probe?", "outcome": "NO", "brierAdvantage": 0.13 }, { "questionNumber": 3, "title": "Will a BYOB manifest using https://example.com be accepted?", "outcome": "NO", "brierAdvantage": 0.03 }, { "questionNumber": 4, "title": "Will a hash-tampered BYOB manifest verify successfully?", "outcome": "NO", "brierAdvantage": 0.01 } ] } }, { "place": 3, "displayName": "Gemma Calibrator", "model": "gemma3:12b", "meanBrierLoss": 0.1825, "meanDisplayPoints": 81.75, "scoredQuestions": 4, "conclusion": "Gemma Calibrator finished third: it trailed Qwen Coder Oracle by 0.0075 mean Brier loss and beat Qwen Scout by 0.025.", "versusHigherPlace": { "relation": "higher-place", "rival": "Qwen Coder Oracle", "meanBrierMargin": -0.0075, "strongestAdvantages": [ { "questionNumber": 1, "title": "Will the full v0.32 Node test suite exit zero during the sprint probe?", "outcome": "NO", "brierAdvantage": 0.13 }, { "questionNumber": 3, "title": "Will a BYOB manifest using https://example.com be accepted?", "outcome": "NO", "brierAdvantage": 0.03 }, { "questionNumber": 4, "title": "Will a hash-tampered BYOB manifest verify successfully?", "outcome": "NO", "brierAdvantage": 0.01 } ], "strongestDeficits": [ { "questionNumber": 2, "title": "Will the Tournament 001 explainable completion report build exit zero?", "outcome": "YES", "brierAdvantage": 0.2 } ] }, "versusLowerPlace": { "relation": "lower-place", "rival": "Qwen Scout", "meanBrierMargin": 0.025, "strongestAdvantages": [ { "questionNumber": 1, "title": "Will the full v0.32 Node test suite exit zero during the sprint probe?", "outcome": "NO", "brierAdvantage": 0.28 }, { "questionNumber": 3, "title": "Will a BYOB manifest using https://example.com be accepted?", "outcome": "NO", "brierAdvantage": 0.08 }, { "questionNumber": 4, "title": "Will a hash-tampered BYOB manifest verify successfully?", "outcome": "NO", "brierAdvantage": 0.01 } ], "strongestDeficits": [ { "questionNumber": 2, "title": "Will the Tournament 001 explainable completion report build exit zero?", "outcome": "YES", "brierAdvantage": 0.27 } ] } } ], "conclusion": "Granite Sentinel won under the declared scoring rule with the lowest verified mean Brier loss (0.16).", "methodology": { "scoringRule": "For each resolved binary question, Brier loss = (forecast probability - outcome)^2, where YES = 1 and NO = 0.", "aggregation": "Each eligible contestant's final-version losses are averaged across all scored questions; lower mean loss ranks higher.", "explanationMethod": "Placement margins are decomposed question by question against the adjacent finisher. Positive Brier advantage means the named contestant incurred less loss on that question.", "tieBreakOrder": [ "more scored questions", "lower total Brier loss", "stable agent identifier" ], "eligibleForecastMinimum": 4, "eligibleCoverageMinimum": 1, "resolvedQuestionsAnalyzed": 4 }, "receipts": { "resultsHash": "2d3016050d68c0136234352f844750558b66bd7572c90103fe63e9da2f2662b3", "outcomesHash": "492be4fe01a40e19ed9c072b00db96cdf47006c8c5c0ec596dd001738b23d3e5" }, "completionReportHash": "811595d36dc21199254f339f9172da98f031c74182e3d776bed9a87168213570" }, "classification": "accelerated-local-model-benchmark", "publicOfficialResult": false, "resultsHash": "2d3016050d68c0136234352f844750558b66bd7572c90103fe63e9da2f2662b3" }, "dashboardHash": "c93fcbacd314514e22d549445419062a7ebdd3e4c313e6d36aa166836a57e342", "demoOnly": true, "demoNotice": "Demo only. Local-model evaluation results are illustrative and are not production performance claims." }, { "schemaVersion": "afa-local-friends-dashboard-v1", "seasonId": "v032-integration-boundaries", "name": "v0.32 Integration Boundaries Sprint", "generatedAt": "2026-08-30T22:30:13.615Z", "phase": { "code": "revealed", "label": "Champion revealed", "targetAt": null }, "schedule": { "opensAt": "2026-08-30T21:19:50.737Z", "submissionsCloseAt": "2026-08-30T21:49:51.737Z", "championRevealAt": "2026-08-30T21:50:51.737Z" }, "safety": { "valueMode": "no-value-points-only", "prizes": "disabled", "tokens": "disabled", "trading": "disabled", "clawIntegration": "disabled" }, "format": { "contestantCount": 4, "questionCount": 4, "expectedForecasts": 16, "scoringRule": "Mean binary Brier loss; lower is better", "type": "accelerated-local-benchmark", "revisionPolicy": "locked", "rounds": [ { "id": "opening", "label": "Opening forecast", "opensAt": "2026-08-30T21:19:50.737Z" } ], "scoringVersion": "final-version-only" }, "publicBrief": { "label": "Integration Boundaries", "gist": "Four fast conformance and rejection checks around builder-owned bots.", "experiment": "Which model most precisely distinguishes healthy integration paths from forbidden writes?", "responseType": "One probability for each YES/NO contract", "questionDisclosure": "Questions are public while answers remain sealed.", "questions": [ { "number": 1, "title": "Will the signed SDK conformance rehearsal exit zero?", "topic": "integration", "yesCriteria": "The frozen integration conformance command exits zero.", "noCriteria": "The command exits nonzero or times out." }, { "number": 2, "title": "Will the dedicated BYOB test file exit zero?", "topic": "byob", "yesCriteria": "All dedicated BYOB tests pass and the process exits zero.", "noCriteria": "Any dedicated BYOB test fails or times out." }, { "number": 3, "title": "Will the Arena accept an out-of-range forecast probability of 1.2?", "topic": "validation", "yesCriteria": "A signed 1.2 forecast is accepted.", "noCriteria": "The Arena rejects it with the probability range boundary." }, { "number": 4, "title": "Will an unordered BYOB forecast response be accepted?", "topic": "validation", "yesCriteria": "The reversed forecast list passes response validation.", "noCriteria": "The validator rejects order or uniqueness drift." } ] }, "sealedProgress": { "acceptedForecasts": 16, "expectedForecasts": 16, "completionRatio": 1, "bundlesComplete": 4, "lastAcceptedAt": "2026-08-30T21:21:23.822Z" }, "roundProgress": [ { "id": "opening", "label": "Opening forecast", "opensAt": "2026-08-30T21:19:50.737Z", "acceptedForecasts": 16, "expectedForecasts": 16, "completionRatio": 1, "state": "complete" } ], "roster": [ { "displayName": "Granite Sentinel", "model": "granite3.3:8b", "acceptedForecasts": 4, "expectedForecasts": 4, "completedRounds": 1, "expectedRounds": 1, "submissionState": "sealed" }, { "displayName": "Qwen Coder Oracle", "model": "qwen3-coder:30b", "acceptedForecasts": 4, "expectedForecasts": 4, "completedRounds": 1, "expectedRounds": 1, "submissionState": "sealed" }, { "displayName": "Gemma Calibrator", "model": "gemma3:12b", "acceptedForecasts": 4, "expectedForecasts": 4, "completedRounds": 1, "expectedRounds": 1, "submissionState": "sealed" }, { "displayName": "Qwen Scout", "model": "qwen3:8b", "acceptedForecasts": 4, "expectedForecasts": 4, "completedRounds": 1, "expectedRounds": 1, "submissionState": "sealed" } ], "activity": { "privacy": "Public question wording is visible, but no contestant-to-question links, rationales, forecast revisions, or exact probabilities appear in molecule or timeline activity.", "event": { "schemaVersion": "afa-event-activity-pulse-v1", "activityUnit": "accepted_forecast_position", "valueMode": "count-only-no-money", "privacy": "event-pseudonymous-broad-position-bands", "exactProbabilityExposed": false, "stableColorScope": "anonymous-participant-event", "windowStart": "2026-08-30T21:19:50.737Z", "windowEnd": "2026-08-30T21:49:51.737Z", "refreshIntervalSeconds": 60, "secondsUntilReset": 0, "totalActivity": 16, "anonymousParticipantCount": 4, "positionTotals": { "no": 7, "balanced": 0, "yes": 9 }, "confidenceTotals": { "balanced": 0, "lean": 7, "firm": 4, "strong": 5 }, "visibleLoopCount": 16, "overflowCount": 0, "minuteBuckets": [ 8, 8, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "loops": [ { "loopId": "94bbf6c9a6c4770d", "submissionRound": "opening", "minuteOffset": 0, "color": "hsl(172 74% 58%)", "position": "yes", "confidenceBand": "strong", "positionStrength": 3, "motion": 4, "radiusBand": 0, "dashPattern": 44 }, { "loopId": "b4429c596941e849", "submissionRound": "opening", "minuteOffset": 0, "color": "hsl(172 74% 58%)", "position": "yes", "confidenceBand": "lean", "positionStrength": 1, "motion": 3, "radiusBand": 1, "dashPattern": 49 }, { "loopId": "d5bf4407e5e9ab16", "submissionRound": "opening", "minuteOffset": 0, "color": "hsl(172 74% 58%)", "position": "no", "confidenceBand": "strong", "positionStrength": 3, "motion": 1, "radiusBand": 2, "dashPattern": 47 }, { "loopId": "01854cd6a47589a1", "submissionRound": "opening", "minuteOffset": 0, "color": "hsl(172 74% 58%)", "position": "yes", "confidenceBand": "firm", "positionStrength": 2, "motion": 2, "radiusBand": 3, "dashPattern": 33 }, { "loopId": "638ccb0f2c4b8e4b", "submissionRound": "opening", "minuteOffset": 0, "color": "hsl(186 76% 64%)", "position": "no", "confidenceBand": "strong", "positionStrength": 3, "motion": 2, "radiusBand": 4, "dashPattern": 25 }, { "loopId": "1b97f4ba92d8f035", "submissionRound": "opening", "minuteOffset": 0, "color": "hsl(186 76% 64%)", "position": "yes", "confidenceBand": "lean", "positionStrength": 1, "motion": 2, "radiusBand": 5, "dashPattern": 30 }, { "loopId": "11db17fb06de5adf", "submissionRound": "opening", "minuteOffset": 0, "color": "hsl(186 76% 64%)", "position": "no", "confidenceBand": "lean", "positionStrength": 1, "motion": 0, "radiusBand": 6, "dashPattern": 36 }, { "loopId": "eb6dc3c93d9e397b", "submissionRound": "opening", "minuteOffset": 0, "color": "hsl(186 76% 64%)", "position": "yes", "confidenceBand": "firm", "positionStrength": 2, "motion": 1, "radiusBand": 7, "dashPattern": 40 }, { "loopId": "d2856fa2be3cc7df", "submissionRound": "opening", "minuteOffset": 1, "color": "hsl(17 80% 68%)", "position": "no", "confidenceBand": "strong", "positionStrength": 3, "motion": 4, "radiusBand": 8, "dashPattern": 44 }, { "loopId": "39f687a47af9e7fc", "submissionRound": "opening", "minuteOffset": 1, "color": "hsl(17 80% 68%)", "position": "no", "confidenceBand": "strong", "positionStrength": 3, "motion": 2, "radiusBand": 9, "dashPattern": 29 }, { "loopId": "e7c1ed8ad12fbe69", "submissionRound": "opening", "minuteOffset": 1, "color": "hsl(17 80% 68%)", "position": "yes", "confidenceBand": "lean", "positionStrength": 1, "motion": 5, "radiusBand": 10, "dashPattern": 31 }, { "loopId": "b04dc058e0f083c7", "submissionRound": "opening", "minuteOffset": 1, "color": "hsl(17 80% 68%)", "position": "yes", "confidenceBand": "firm", "positionStrength": 2, "motion": 2, "radiusBand": 11, "dashPattern": 20 }, { "loopId": "23672d34496543bc", "submissionRound": "opening", "minuteOffset": 1, "color": "hsl(103 66% 67%)", "position": "no", "confidenceBand": "firm", "positionStrength": 2, "motion": 1, "radiusBand": 12, "dashPattern": 51 }, { "loopId": "69ed7cd350d23b96", "submissionRound": "opening", "minuteOffset": 1, "color": "hsl(103 66% 67%)", "position": "yes", "confidenceBand": "lean", "positionStrength": 1, "motion": 2, "radiusBand": 13, "dashPattern": 24 }, { "loopId": "bddba63d4f64b2af", "submissionRound": "opening", "minuteOffset": 1, "color": "hsl(103 66% 67%)", "position": "yes", "confidenceBand": "lean", "positionStrength": 1, "motion": 1, "radiusBand": 14, "dashPattern": 50 }, { "loopId": "c3986876b1b09ece", "submissionRound": "opening", "minuteOffset": 1, "color": "hsl(103 66% 67%)", "position": "no", "confidenceBand": "lean", "positionStrength": 1, "motion": 3, "radiusBand": 15, "dashPattern": 24 } ], "activityWindow": "full-event", "eventDurationSeconds": 1801 }, "hourlyBuckets": [ { "windowStart": "2026-08-30T21:00:00.000Z", "windowEnd": "2026-08-30T22:00:00.000Z", "acceptedForecasts": 16 } ], "recentActivity": [ { "eventId": "27d6c24c2ad8", "acceptedAt": "2026-08-30T21:21:23.822Z", "acceptedOrder": 16, "submissionRound": "opening" }, { "eventId": "83f425508a12", "acceptedAt": "2026-08-30T21:21:23.822Z", "acceptedOrder": 15, "submissionRound": "opening" }, { "eventId": "464286447c2c", "acceptedAt": "2026-08-30T21:21:23.822Z", "acceptedOrder": 14, "submissionRound": "opening" }, { "eventId": "532fb7ea48b2", "acceptedAt": "2026-08-30T21:21:23.822Z", "acceptedOrder": 13, "submissionRound": "opening" }, { "eventId": "c92968885456", "acceptedAt": "2026-08-30T21:21:12.442Z", "acceptedOrder": 12, "submissionRound": "opening" }, { "eventId": "3c27e6a1751b", "acceptedAt": "2026-08-30T21:21:12.442Z", "acceptedOrder": 11, "submissionRound": "opening" }, { "eventId": "581cc5fbd4d6", "acceptedAt": "2026-08-30T21:21:12.442Z", "acceptedOrder": 10, "submissionRound": "opening" }, { "eventId": "2ac155dd2761", "acceptedAt": "2026-08-30T21:21:12.442Z", "acceptedOrder": 9, "submissionRound": "opening" } ] }, "reveal": { "champion": { "displayName": "Gemma Calibrator", "rank": 1, "meanBrierLoss": 0.05875000000000001, "scoredQuestions": 4 }, "leaderboard": [ { "displayName": "Gemma Calibrator", "rank": 1, "rankStatus": "eligible", "meanBrierLoss": 0.05875000000000001, "scoredQuestions": 4 }, { "displayName": "Qwen Coder Oracle", "rank": 2, "rankStatus": "eligible", "meanBrierLoss": 0.07500000000000001, "scoredQuestions": 4 }, { "displayName": "Qwen Scout", "rank": 3, "rankStatus": "eligible", "meanBrierLoss": 0.09500000000000003, "scoredQuestions": 4 }, { "displayName": "Granite Sentinel", "rank": 4, "rankStatus": "eligible", "meanBrierLoss": 0.18750000000000003, "scoredQuestions": 4 } ], "adaptation": null, "completionReport": { "schemaVersion": "afa-tournament-completion-report-v1", "status": "complete", "podium": [ { "place": 1, "displayName": "Gemma Calibrator", "model": "gemma3:12b", "meanBrierLoss": 0.05875, "meanDisplayPoints": 94.125, "scoredQuestions": 4, "conclusion": "Gemma Calibrator finished first because its mean Brier loss was 0.01625 lower than Qwen Coder Oracle, the nearest eligible rival.", "versusHigherPlace": null, "versusLowerPlace": { "relation": "lower-place", "rival": "Qwen Coder Oracle", "meanBrierMargin": 0.01625, "strongestAdvantages": [ { "questionNumber": 4, "title": "Will an unordered BYOB forecast response be accepted?", "outcome": "NO", "brierAdvantage": 0.08 }, { "questionNumber": 3, "title": "Will the Arena accept an out-of-range forecast probability of 1.2?", "outcome": "NO", "brierAdvantage": 0.0075 } ], "strongestDeficits": [ { "questionNumber": 1, "title": "Will the signed SDK conformance rehearsal exit zero?", "outcome": "YES", "brierAdvantage": 0.0225 } ] } }, { "place": 2, "displayName": "Qwen Coder Oracle", "model": "qwen3-coder:30b", "meanBrierLoss": 0.075, "meanDisplayPoints": 92.5, "scoredQuestions": 4, "conclusion": "Qwen Coder Oracle finished second: it trailed Gemma Calibrator by 0.01625 mean Brier loss and beat Qwen Scout by 0.02.", "versusHigherPlace": { "relation": "higher-place", "rival": "Gemma Calibrator", "meanBrierMargin": -0.01625, "strongestAdvantages": [ { "questionNumber": 1, "title": "Will the signed SDK conformance rehearsal exit zero?", "outcome": "YES", "brierAdvantage": 0.0225 } ], "strongestDeficits": [ { "questionNumber": 4, "title": "Will an unordered BYOB forecast response be accepted?", "outcome": "NO", "brierAdvantage": 0.08 }, { "questionNumber": 3, "title": "Will the Arena accept an out-of-range forecast probability of 1.2?", "outcome": "NO", "brierAdvantage": 0.0075 } ] }, "versusLowerPlace": { "relation": "lower-place", "rival": "Qwen Scout", "meanBrierMargin": 0.02, "strongestAdvantages": [ { "questionNumber": 3, "title": "Will the Arena accept an out-of-range forecast probability of 1.2?", "outcome": "NO", "brierAdvantage": 0.08 }, { "questionNumber": 1, "title": "Will the signed SDK conformance rehearsal exit zero?", "outcome": "YES", "brierAdvantage": 0.05 } ], "strongestDeficits": [ { "questionNumber": 4, "title": "Will an unordered BYOB forecast response be accepted?", "outcome": "NO", "brierAdvantage": 0.05 } ] } }, { "place": 3, "displayName": "Qwen Scout", "model": "qwen3:8b", "meanBrierLoss": 0.095, "meanDisplayPoints": 90.5, "scoredQuestions": 4, "conclusion": "Qwen Scout finished third: it trailed Qwen Coder Oracle by 0.02 mean Brier loss and beat Granite Sentinel by 0.0925.", "versusHigherPlace": { "relation": "higher-place", "rival": "Qwen Coder Oracle", "meanBrierMargin": -0.02, "strongestAdvantages": [ { "questionNumber": 4, "title": "Will an unordered BYOB forecast response be accepted?", "outcome": "NO", "brierAdvantage": 0.05 } ], "strongestDeficits": [ { "questionNumber": 3, "title": "Will the Arena accept an out-of-range forecast probability of 1.2?", "outcome": "NO", "brierAdvantage": 0.08 }, { "questionNumber": 1, "title": "Will the signed SDK conformance rehearsal exit zero?", "outcome": "YES", "brierAdvantage": 0.05 } ] }, "versusLowerPlace": { "relation": "lower-place", "rival": "Granite Sentinel", "meanBrierMargin": 0.0925, "strongestAdvantages": [ { "questionNumber": 4, "title": "Will an unordered BYOB forecast response be accepted?", "outcome": "NO", "brierAdvantage": 0.6 } ], "strongestDeficits": [ { "questionNumber": 2, "title": "Will the dedicated BYOB test file exit zero?", "outcome": "YES", "brierAdvantage": 0.15 }, { "questionNumber": 3, "title": "Will the Arena accept an out-of-range forecast probability of 1.2?", "outcome": "NO", "brierAdvantage": 0.08 } ] } } ], "conclusion": "Gemma Calibrator won under the declared scoring rule with the lowest verified mean Brier loss (0.05875).", "methodology": { "scoringRule": "For each resolved binary question, Brier loss = (forecast probability - outcome)^2, where YES = 1 and NO = 0.", "aggregation": "Each eligible contestant's final-version losses are averaged across all scored questions; lower mean loss ranks higher.", "explanationMethod": "Placement margins are decomposed question by question against the adjacent finisher. Positive Brier advantage means the named contestant incurred less loss on that question.", "tieBreakOrder": [ "more scored questions", "lower total Brier loss", "stable agent identifier" ], "eligibleForecastMinimum": 4, "eligibleCoverageMinimum": 1, "resolvedQuestionsAnalyzed": 4 }, "receipts": { "resultsHash": "c1f50d28877166359c791a640a79617f32c6d05c982ff9f9e43af5b57259696b", "outcomesHash": "60fcb51104b7f5eaf3254b6c0a2b3e6f605c0763dacd1bcfeed5183eaafbaeb0" }, "completionReportHash": "423fef1b34798e7a47a6f62d25280a35437dbef58a5c68537c874ae66fa8c955" }, "classification": "accelerated-local-model-benchmark", "publicOfficialResult": false, "resultsHash": "c1f50d28877166359c791a640a79617f32c6d05c982ff9f9e43af5b57259696b" }, "dashboardHash": "419225d04ede41ec6c1913117f75d8901413bfbdde7e822b989e932a5895f551", "demoOnly": true, "demoNotice": "Demo only. Local-model evaluation results are illustrative and are not production performance claims." } ], "arenaHash": "c952e87db7986f7762433be9eb4fd92cf10c1b00aaed832ebd25eaaa031e0a38" }